山东大学学报 (工学版) ›› 2024, Vol. 54 ›› Issue (1): 83-90.doi: 10.6040/j.issn.1672-3961.0.2022.344
• 机器学习与数据挖掘 • 上一篇
曹宇慧,黄昱泽*,冯北鹏,张淼,郭珍珍
CAO Yuhui, HUANG Yuze*, FENG Beipeng, ZHANG Miao, GUO Zhenzhen
摘要： 针对边缘计算中终端算力不足、资源有限和时延较大的问题,提出一种基于深度强化学习的物联网服务协同卸载方法。通过3种不同的卸载方式建立时延模型,挖掘服务之间的关联关系,对关联服务进行协同卸载,加入关联服务的通信时延以建立完善的卸载时延模型,结合整体模型考虑卸载率的取值以及关联服务如何协同卸载使时延最小,从而实现服务调用时延和服务间通信时延的最小化。试验结果表明,与其他算法相比,该算法在获取最优服务卸载策略的同时,系统总服务时延能降低20%左右。
中图分类号:
| [1] CANO J C, BERRIOS V, GARCIA B, et al. Evolution of IoT: an industry perspective[J]. IEEE Internet of Things Journal, 2018, 1(2): 12-17. [2] RUAN J, WANG Y, CHAN F T S, et al. A life cycle framework of green IoT-based agriculture and its finance, operation, and management issues[J]. IEEE Communications Magazine, 2019, 57(3): 90-96. [3] RIAHI A, CHALLAL Y, MOYAL P, et al. A game theoretic approach for privacy preserving model in IoT-based transportation[J]. IEEE Transactions on Intelligent Transportation Systems, 2019, 20(12): 4405-4414. [4] YONGJOH S, SO-IN C, KOMPUNT P, et al. Development of an internet-of-healthcare system using blockchain[J]. IEEE Access, 2021, 9: 113017-113031. [5] POPA D, POP F, SERBANESCU C, et al. Deep learning model for home automation and energy reduction in a smart home environment platform[J]. Neural Computing and Applications, 2019, 31: 1317-1337. [6] DIN I U, GUIZANI M, HASSAN S, et al. The internet of things: a review of enabled technologies and future challenges[J]. IEEE Access, 2019, 7: 7606-7640. [7] ARMBRUST M, FOX A, GRIFFITH R, et al. A view of cloud computing[J]. Communications of the ACM, 2010, 53(4): 50-58. [8] 施巍松, 孙辉, 曹杰, 等. 边缘计算:万物互联时代新型计算模型[J]. 计算机研究与发展, 2017, 54(5): 907-924. SHI Weisong, SUN Hui, CAO Jie, et al. Edge computing: a new computing model in the internet of everything era [J]. Computer Research and Development, 2017, 54(5): 907-924. [9] SHI W S, CAO J, ZHANG Q, et al. Edge computing: vision and challenges[J]. IEEE Internet of Things Journal, 2016, 3(5): 637-646. [10] AHMED A, AHMED E. A survey on mobile edge computing[C] //Proceedings of the 10th International Conference on Intelligent Systems and Control. Coimbatore, India: IEEE, 2016: 1-8. [11] ZHANG K, LENG S P, HE Y J, et al. Mobile edge computing and networking for green and low latency internet of things[J]. IEEE Communications Magazine, 2018, 56(5): 344-352. [12] WU Z, LU Z, HUNG P C K, et al. QaMeC: a QoS-driven iovs application optimizing deployment scheme in multimedia edge clouds[J]. Future Generation Computer Systems, 2019, 92: 17-28. [13] ZHANG H H, LI J L, YUAN Q. Edge service migration for vehicular networks based on multi-agent deep reinforcement learning[C] //Technologies and Services Toward Smart Cities: 6th International Conference. Kaohsiung, Taiwan, China: Lecture Notes in Computer Science, 2019: 344-352. [14] 葛海波, 李文浩, 冯安琪,等. 改进遗传算法的边缘计算卸载策略[J]. 西安邮电大学学报, 2020, 25(3): 7-13. GE Haibo, LI Wenhao, FENG Anqi, et al. Improved genetic algorithm for edge computing offloading strategy [J]. Journal of Xi'an University of Posts and Telecommunications, 2020, 25(3): 7-13. [15] 张文柱, 曹琲琲, 余静华. 移动边缘计算中一种多用户计算卸载方法[J]. 西安电子科技大学学报, 2020, 47(6): 131-138. ZHANG Wenzhu, CAO Beibei, YU Jinghua. A multi-user computing offloading method in mobile edge computing [J]. Journal of Xidian University, 2020, 47(6): 131-138. [16] 罗斌. MEC计算卸载策略的研究与应用[D]. 沈阳:中国科学院大学,2020. LUO Bin. Research and application of MEC computing offloading strategy[D]. Shenyang: University of Chinese Academy of Sciences, 2020. [17] 詹文翰. 移动边缘网络计算卸载调度与资源管理策略优化研究[D]. 成都:电子科技大学, 2020. ZHAN Wenhan. Research on computing offload scheduling and resource management strategy optimization in mobile edge network[D]. Chengdu: University of Electronic Science and Technology of China, 2020. [18] HUANG Y Z, HUANG J W, CHEN J L, et al. Poster: interacting data-intensive services mining and placement in mobile edge clouds[C] //Proceedings of the 23rd Annual International Conference on Mobile Computing and Networking. New York, USA: Association for Computing Machinery, 2017: 558-560. [19] HUANG Y Z, HUANG J W, LIU C, et al. PFPMine: a parallel approach for discovering interacting data entities in data-intensive cloud workflows[J]. Future Generation Computer Systems, 2020, 113: 474-487. [20] RICHARD S, DAVID M, SATINDER S, et al. Policy gradient methods for reinforcement learning with function approximation[C] //Neural Information Processing Systems(NIPS). Cambridge, MA, USA: MIT Press, 1999: 1057-1063. [21] MUIH V, KAVUKCUOGLUC K, SILVER D, et al. Human-level control through deep reinforcement learning[J]. Nature, 2015, 518: 529-533. [22] 葛志诚, 徐恪, 陈靓. 一种移动内容分发网络的分层协同缓存机制[J]. 计算机学报, 2018, 41(12): 2769-2786. GE Zhicheng, XU Ke, CHEN Liang, et al. A hierarchical cooperative caching strategy for mobile content delivery network[J]. Chinese Journal of Computers, 2018, 41(12): 2769-2786. [23] LUO Q Y, LI C L, SHI W S, et al. Self-learning based computation offloading for internet of vehicles: model and algorithm[J]. IEEE Transactions on Wireless Communications, 2021, 20(9): 5913-5925. [24] HUANG J W, LÜ B F, WU Y A, et al. Dynamic admission control and resource allocation for mobile edge computing enabled small cell network[J]. IEEE Transactions on Vehicular Technology, 2022, 71(2): 1964-1973. |
| [1] | 赵晓焱,高源志,张佳乐,张俊娜,袁培燕. 一种基于轨迹预测的车联网边缘卸载策略[J]. 山东大学学报 (工学版), 2024, 54(1): 52-62. |
| [2] | 钱程,赵淦森,罗浩宇. MEC中面向动态环境的工作流D2D协同卸载方法[J]. 山东大学学报 (工学版), 2022, 52(4): 45-53. |
|
||
